Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specific device or package

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Temple
    0.40
    Stocks
    0.39
    Aug
    0.39
    quarters
    0.39
    Greek
    0.39
    anges
    0.38
    Dol
    0.38
    guj
    0.38
    UserRepository
    0.38
    중에
    0.38
    POSITIVE LOGITS
     চিত
    0.40
     scheduling
    0.39
     optimizes
    0.39
     anime
    0.39
     '=',
    0.38
     timing
    0.38
     Tells
    0.38
     saline
    0.37
     adjusts
    0.37
     performance
    0.37
    Act Density 0.000%

    No Known Activations